Sign in with
Sign up | Sign in
Your question

Multiple Video Card, Separate Monitors, How does it work?

Last response: in Graphics & Displays
Share
a b U Graphics card
a b C Monitor
March 7, 2013 3:21:23 PM

I posted this over on another forum, but figured i would ask here as well . . .

I have two monitors, one is plugged in to my GTX 670 as my main display. I have a second one plugged in to my on board (HD4000) which i just use for general 2D windows stuff, like Voice chat sofware, forums, reading PDF files etc. I had originally set it up this way as I didn't want the second monitor having an effect on performance of the main monitor, even if it was very little. I also wanted access to quick sync without using Virtu, which I'm not sure will end up working. This plan was dashed when I was playing with some different settings in some games and flipped to window mode, at which point I noticed that I can take a game window and place it so that it's half on each monitor, but frame rate doesn't seem to be affected.

So a few questions popped up. Primarily, how does this even function? Is the 3D data being processed and rendered by both cards anyway, or does the primary cards frame buffer get copied to main memory for display by the second card, or does the second card just address the memory of the main card for use like an overlay? I can't really wrap my head around the data flow to even guess how it's working. Does it work differently if two dedicated cards are used? (Say my 670 and my old 5770?)

I couldn't find any benchmarking data that tests setups like these, so how does this effect performance? Can anyone point to links that benchmark things like both monitors on one card, the secondary on a second card, the secondary on the on board? I haven't been able to locate any good resources. I will probably end up doing it myself, but I would really like to read up on the topic some before hand.
a c 188 U Graphics card
a c 98 C Monitor
March 7, 2013 4:45:30 PM

It is being processed by the primary gpu, the video feed is just going to another video output which just happens to be through another gpu. The 2nd gpu isn't processing or using extra memory, it is a passthrough. It would be the same with any 2 gpus not working together or even with 2 gpus sli/cf on software that doesn't support sli/cf. Although sli/cf with supported software is still passing off frames through each other if the displays are on each.

Displaying a monitor takes very little power which is why even older integrated can run 1080p or higher resolutions fine. You could test it yourself as there are no benchmarks. There shouldn't be a noticeable difference unless doing something that actually takes a bit of power.
m
0
l
a b U Graphics card
a b C Monitor
March 7, 2013 5:21:40 PM

So how about a situation where I launch the application on my primary display and then move the window fully to the second . . . is it still rendered by the first card, and if so, I still don't understand how the data gets from the first card to the second. You say it passes through.... passes through what?



m
0
l
Related resources
a c 188 U Graphics card
a c 98 C Monitor
March 8, 2013 12:14:12 AM

Software will always use the primary unless specified otherwise. The processed data is sent back through the pcie to the mobo output.
m
0
l
a b U Graphics card
a b C Monitor
March 8, 2013 12:29:26 AM

So you are saying the second video card directly reads the frame buffer of the primary card?
m
0
l
a b U Graphics card
a b C Monitor
March 8, 2013 1:17:52 AM

k1114 said:
Software will always use the primary unless specified otherwise. The processed data is sent back through the pcie to the mobo output.


I'm also not convinced all software works as you described. My first benchmark attempt was using PassMark Software Performance Test 8 using their advanced 3D test. I did 4 runs total, and I chose 180 second tests because I had to manually move the window around at the start so I wanted as much testing time to remove that from the average as I could. In all 4 runs the Video Card stated it was to be run on the 670.

I used the DX10 test, 1366x768, overlay off, vsync off, windows mode, 50 islands/250 meteors, 180 second tests.

Run one I moved the window on my main screen (to be fair, since I needed to move it in all 3 other tests) and it popped out:
33.18 fps / 30.14ms per frame / 0.95ms Jitter (3.16%)

Run two I moved the window to the second monitor, it came up as:
6.26 fps / 159.85ms per frame / 6.32ms Jitter (3.95%)

Test 3 I moved the window so that it was approx 2/3 on the primary, and 1/3 on the secondary:
21.03 fps / 47.56ms per frame / 2.85ms Jitter (6.00%)

Test 4, 1/3 Primary and 2/3 Secondary:
6.06 fps / 164.97ms per frame / 3.95ms Jitter (2.40%)

So, obviously it's not always completely done on the primary card. I'm kind of back to being confused, since when I first noticed the behavior it was in a game which I assumed would either have it's frame rate plummet, go black, or have some other bad thing happen didn't seem to be affected at all.


m
0
l
a c 188 U Graphics card
a c 98 C Monitor
March 8, 2013 5:56:22 AM

Look at your igpu usage and tell me what you see. You might also want to look at 670 usage too. The decrease in performance can be caused from the passthrough. You could always run just the igpu and if the workload is split, it would be higher fps together. Did you move them before you tested and did not move it while testing?

I didn't say software couldn't use both but games will not distribute workload, they are not programmed to do so. Also passmark is unreliable as a gpu test.
m
0
l
a b U Graphics card
a b C Monitor
March 8, 2013 4:25:38 PM

k1114 said:
Look at your igpu usage and tell me what you see. You might also want to look at 670 usage too. The decrease in performance can be caused from the passthrough. You could always run just the igpu and if the workload is split, it would be higher fps together. Did you move them before you tested and did not move it while testing?

I didn't say software couldn't use both but games will not distribute workload, they are not programmed to do so. Also passmark is unreliable as a gpu test.


Do you know of any tools that can monitor CPU, each GPU, system memory, and each video cards memory all at the same time . . . preferably logging it?
m
0
l
!